Learning Semantically and Additively Compositional Distributional Representations
arXiv:1606.02461
Abstract
This paper connects a vector-based composition model to a formal semantics, the Dependency-based Compositional Semantics (DCS). We show theoretical evidence that the vector compositions in our model conform to the logic of DCS. Experimentally, we show that vector-based composition brings a strong ability to calculate similar phrases as similar vectors, achieving near state-of-the-art on a wide range of phrase similarity tasks and relation classification; meanwhile, DCS can guide building vectors for structured queries that can be directly executed. We evaluate this utility on sentence completion task and report a new state-of-the-art.
arXiv commentto appear in ACL2016
References in corpus (6)
- Efficient Estimation of Word Representations in Vector Space
- From Frequency to Meaning: Vector Space Models of Semantics
- Classifying Relations by Ranking with Convolutional Neural Networks
- Traversing Knowledge Graphs in Vector Space
- A Study of Entanglement in a Categorical Framework of Natural Language
- Category-Theoretic Quantitative Compositional Distributional Models of Natural Language Semantics